A kind of system of highway fee evasion inspection
Technical field
The present invention relates to a kind of computer external data process field, what particularly a kind of highway fee evasion was checked is
System.
Background technology
In recent years, with expanding economy, expressway construction and O&M enter a new stage.The high speed newly opened
Highway section is more and more, and mileage open to traffic is increasingly longer, and freeway traffic is facilitated increasingly, public at a high speed on all kinds of lorries and car
Road is also more and more, but also occurs in that some discordant notes simultaneously.Some illegal drivers or staff drive in interests
Under making, various illegal fee evasion activities are carried out, wherein to change card, the fee evasion behavior such as to fall to block the most universal.It is non-for these
Method fee evasion behavior, current highway unit of operation lacks effective method to be managed and specification, often passes through afterwards
Manually related data is handled, inefficiency, effect is not obvious.
Meanwhile, the pattern recognition device of freeway toll station gateway at night the period due to by light and light filling not
The influence of foot etc., vehicle and Car license recognition rate be not high, the problem of so actual, directly affects the discriminating energy to entering and exiting vehicle
Power, so that illegal fee evasion vehicle has an opportunity to take advantage of.
In view of the above-mentioned problems, currently existing scheme includes at present:
Method 1:Analyzed by the comparison manually entered according to some retrieval information from background data base under line, specific inspection
Rope information, can for example incidence relation of Car license recognition information and visa card etc..
Method 2:Vehicle is identified by gateway license plate recognition device, and the relation of the visa card with being provided is straight
The comparison of row backstage is tapped into, differentiates fee evasion situation with this.
The shortcoming of prior art is as follows:
Method 1:Compared and analyzed by manually entering under line, efficiency is low, and cost of labor is high, is not suitable with current art and application
Development trend.
Method 2:This method is the method designed based on the errorless premise of Car license recognition, but actual conditions are especially in evening
The upper period, the accuracy rate of vehicle identification is not high, and exactly has many illegal fee evasion vehicles to be come in and gone out at a high speed in certain evening hours section,
Therefore the usage scenario of this method and targeted object ratio are relatively limited.
In addition, the problem of prior art also has following:
(1) highway lane toll system is main to handle charge operation as first, and what is functionally focused on is charge operation
With the processing of event, often lack for change card, fall card etc. fee evasion behavior comprehensive consideration, be particularly difficult for toll collector
Offer is a kind of can to carry out the function services of on-site examination to fee evasion vehicle;
(2) although at present numerous highways to entry and exit vehicle carry out video capture, captured image by
To the influence of light etc., the discrimination of vehicle is not high, and these image informations only make as the incidental information of charge record
With calling and not yet realize at present between gateway.
The content of the invention
Goal of the invention:The technical problems to be solved by the invention are public there is provided a kind of high speed in view of the shortcomings of the prior art
The system of road fee evasion inspection.
In order to solve the above-mentioned technical problem, the invention discloses a kind of system of highway fee evasion inspection, including:
Entrance vehicle information collecting device, the information of vehicles for gathering expressway access;
Export vehicle information collecting device, the information of vehicles for gathering expressway exit;
Portal server, leads to for storing the information of vehicles that entrance vehicle information collecting device is collected, and combining vehicle
Row card sets up vehicle and enters table;
Output port server, leads to for storing the information of vehicles that outlet vehicle information collecting device is collected, and combining vehicle
Row card sets up vehicle and goes out table;Output port server is set up and preserves warning data storehouse DBW1 and doubtful vehicle database DBW2;
Output port server enters table according to vehicle and vehicle goes out table, determines whether fee evasion vehicle;
Business platform, the information of vehicles record reported according to output port server is set up and preserves doubtful vehicle information database
DBW, and mark doubtful fee evasion vehicle.
In the present invention, the information of vehicles of entrance vehicle information collecting device collection includes weight W1, time T1, vehicle image
P1;Exporting the information of vehicles of vehicle information collecting device collection includes weight W2, time T2, vehicle image P2.
In the present invention, vehicle S1 and car plate D1 to vehicle image P1 identifications by obtaining;It is right that vehicle S2 and car plate D2 pass through
Vehicle image P2 identifications are obtained.
In the present invention, information of vehicles table includes into table TableEnter and goes out table TableExit;
Entering table TableEnter includes:Visa card C, weight W1, time T1, vehicle S1, car plate D1, Car license recognition rate u1,
Vehicle image P1;
Going out table TableExit includes:Visa card C, weight W2, time T2, vehicle S2, car plate D2, Car license recognition rate u2, car
Image P2.
In the present invention, vehicle reaches expressway exit, and output port server judges whether vehicle meets one of following condition,
It is determined as fee evasion vehicle if meeting;
Condition 1:|W2-W1|>A, a change the threshold value for passing in and out weight change to judge that vehicle is illegally shifted, and set scope
For 150kg~300kg;
Condition 2:b>[L/ (T2-T1)] or [L/ (T2-T1)]>C, L are the expressway access and outlet that the vehicle enters
Corresponding highway distance, b be highway on refer to minimum travel speed, set scope be 2km/h~5km/h or other
Reasonable value, c is the maximum travel speed that refers on highway, sets that scope is 120km/h~130km/h or other are reasonable
Numerical value;
Condition 3:Vehicle S1 is different from vehicle S2;
Condition 4:If u1>N, and u2>N, and D1 ≠ D2, n are for the correct discrimination percentage number of Car license recognition
Value, n values are 99% or other reasonable values;
Condition 5:The vehicle similarity for calculating vehicle image P1 and P2 is dealt with:If similarity is less than g1, it is determined as
Fee evasion vehicle;If g2>g>G1, then be determined as doubtful fee evasion vehicle, and table TableEnter and entering for the vehicle is out into table
TableExit is merged into conjunction table is gone out, while being stored in the warning data storehouse DBW1 of output port server;Wherein g1 meaning be than
It is that can confirm the situation of dissmilarity to two vehicle images;And g2 is then to compare two vehicle images for doubtful dissimilar situation, example
It is 50% or other reasonable values such as to set g2;G1 spans 15%~25% or other reasonable values;G2 spans
45%~55% or other reasonable values;
Condition 6:If u1>N or u2>N, output port server sets up doubtful database D BW2 and in doubtful database D BW2
U1 (is worked as with licence plate>During n, D1 licence plates are used;Work as u2>During n, with D2 licence plates) corresponding table information is set up with reference to doubtful number of times for index,
And cumulative mark is carried out to the doubtful number of times of licence plate, and upload business platform;If the doubtful number of times of licence plate exceedes threshold value, sentence
It is set to fee evasion vehicle, is otherwise determined as legal vehicle;Threshold value span 3~20 or other reasonable values.
In the present invention, in the condition 6, business platform performs following steps:
Step a:Business platform receive output port server upload warning data storehouse DBW1 in it is doubtful enter out conjunction table and doubt
Likelihood data storehouse DBW2, foundation includes the database D BW of corresponding doubtful marking of cars table information;
Step b:Judge whether there is corresponding car plate D1 in the DBW databases of business platform, if not provided, into step c;
If any then into step d;
Step c:Newly-built car plate D1 for index doubtful information of vehicles table (【D1,v】, its doubtful number of times is set to 1;
Step d:Will the doubtful information of vehicles table of correspondence (【D1,v】) in car plate D1 doubtful number of times v add 1, and judge, such as
Really doubtful number of times exceedes the thresholding of setting, is determined as fee evasion vehicle, and be automatically pushed to the doubtful situation of staff's progress examination & verification
Processing, and according to circumstances can transfer specifying information from related charge station's server;Otherwise it is determined as legal vehicle.
Beneficial effect:The present invention carries out the analyzing and processing of big data using computer, manually compares other side compared to more traditional
Formula is more accurate, more efficient.
Brief description of the drawings
The present invention is done with reference to the accompanying drawings and detailed description and further illustrated, of the invention is above-mentioned
And/or otherwise advantage will become apparent.
Fig. 1 is embodiment system structure diagram.
Fig. 2 is embodiment overall procedure schematic diagram.
Fig. 3 is that comparative analysis method schematic diagram is screened in embodiment fee evasion.
Fig. 4 is embodiment business platform handling process.
Embodiment
Embodiment
The system that the present embodiment is applied to highway fee evasion inspection includes being applied to freeway toll station acquisition vehicle
The harvester of information, and business platform;As shown in figure 1, harvester is divided into entrance harvester subsystem and outlet is adopted
Acquisition means subsystem, and each harvester subsystem includes Weight acquisition module and image capture module;Wherein weight
Acquisition module is just as the weighbridge equipment at freeway toll station, and image capture module is just as expressway tol lcollection
The camera device stood, the weight information (W1, W2) and image information (P1, P2) that this two kind equipment is gathered will be respectively stored in
In corresponding portal server 1 and output port server 2, the visa card card number information C with the related corresponding car of above- mentioned information, with
And vehicle enters high speed time T1, vehicle rolls the time T2 of high speed away from;Simultaneously according to similar such as a kind of patented technology " Car license recognition
The method and system " (patent No.:200710120602.0) etc. the existing ripe image procossing of in the market method, for vehicle figure
Picture information (P1, P2) analytic solution obtains corresponding vehicle information (S1, S2), and wherein S1 and S2 are as being heavy truck, lesser calorie, small sedan-chair
Car, SUV etc., wherein vehicle identification are commonly considered as more accurately, even if being influenceed by brightness etc., are charged out in high speed
Should be that can ensure the accuracy of vehicle cab recognition under the conditions of entrance light filling;In addition, according to such as software product " extra large river Car license recognition
The ripe Car license recognition processing method such as software " obtains corresponding license board information for vehicle image information (P1, P2) analytic solution
(D1, D2), wherein D1 and D2 are license board information of the vehicle according to obtained by the image information analysis of image acquisition device, but by
Influenceed to light etc., although then have higher discrimination, but especially evening on daytime, car plate discrimination can be by high speed
Influence, therefore D1 and D2 here can not directly compare out the result of examination many when.Gathered by similar license plate image
Method and device (application number:201410745917.4) or a kind of licence plate recognition method and system (application number:
200710120602.0) image processing algorithm as and method have the output of a discrimination to parse during car plate, be such as
99% or 30% equal percentage data, its span is from 0-100%.
Above- mentioned information unification is combined in the portal server 1 and the corresponding informance table of output port server 2 of corresponding visa card,
I.e. each visa card has two corresponding information tables, as follows:
Enter table TableEnter:【Visa card C, weight W1, time T1, vehicle S1, car plate D1, Car license recognition rate u1, vehicle
Image P1】;
Go out table TableExit:【Visa card C, weight W2, time T2, vehicle S2, car plate D2, Car license recognition rate u2, vehicle
Image P2】.
Server 1 is to be used for tissue letter related to storage vehicle Ru Chu charge stations for respective charge station to server 2
Breath, and the relevant information of visa card can be corresponded in the server of outlet server in station call entry website in a network.
As shown in Figure 2 to 4, the present embodiment system performs following steps:
Step 1:Vehicle is driven into after highway from entrance, and in porch, harvester gets vehicle-related information, and
By in the unified addition table TableEneter of itself and the current card information provided etc., TableEnter is formed:【Visa card C1, weight
Measure W1, time T1, vehicle S1, car plate D1, Car license recognition rate u1, vehicle image P1】;Wherein, vehicle S1 is according to vehicle image
P1 processing gained, this image procossing can be according to mature technology recited above;Meanwhile, related table information can be sent to
In business platform, used for being further analysed;
Step 2:This car reaches expressway exit charge station, and vehicle phase is got by harvester in outlet cash desk
The information of pass, and by the unified addition table TableExit of itself and the current card information provided etc., form TableExit:【It is logical
Row blocks C, weight W2, time T2, vehicle S2, car plate D2, Car license recognition rate u2, vehicle image P2】;Wherein, vehicle S2 is foundation
Vehicle image P2 processing gained, this image procossing can be according to ripe technology;
Step 3:Before vehicle is not paid dues, what server 2 called correspondence visa card C entrance enters table information, goes out oral
Business device judges whether vehicle meets one of following condition, and fee evasion vehicle is determined as if meeting:
Condition 3-1, such as | W2-W1 |>A, then it is fee evasion vehicle to be directly determined as the car, into step 4;Wherein a is judgement
Vehicle illegally shifts the threshold value for changing turnover weight change, such as may be configured as 200kg~300kg or other reasonable values;
Condition 3-2, expressway access information of the output port server in vehicle pass-through card, from GIS-Geographic Information System or
Reasonable operating range L, such as b that the vehicle is driven between the entrance and exit of this section of highway are obtained in other systems>[L/
(T2-T1)] or [L/ (T2-T1)]>C, then be directly entered step 4;It should be noted that b here is reasonable on highway
Minimum travel speed, such as may be configured as 2km/h or other numerical value;And c is rational maximum travel speed on highway, such as
It may be configured as 130km/h or other numerical value;
Condition 3-3, vehicle cab recognition information such as S1 is different from S2, then is directly entered step 4;;
Condition 3-4, if u1>N, and u2>N, if while D1 ≠ D2, is directly entered step 4;Wherein n is to be defaulted as
The correct discrimination percentages of Car license recognition, the numerical value can be set, as acquiescence may be configured as n=95% or other conjunctions
Manage numerical value;
Condition 3-5, based on such as patented technology " image partition method based on the similarity interaction mechanism " (patent No.:
Etc. 201210109158.3) method of ripe image similarity analysis to vehicle image P1 and P2 vehicle similarity work at
Reason, including the similarity processing to license plate image, if similarity is less than g1, into step 4;If similarity is in g1
(the g2 between g2>G1), then it is assumed that the vehicle be doubtful fee evasion vehicle, then by this enter table and go out table merge into one it is " doubtful
Enter out conjunction table ", while the table is stored in the warning data storehouse DBW1 of output port server, enters out conjunction table wherein doubtful and include:【It is logical
Row blocks C, weight W1, time T1, vehicle S1, car plate D1, Car license recognition rate u1, vehicle image P1, weight W2, time T2, vehicle
S2, car plate D2, Car license recognition rate u2, vehicle image P2】, carry out condition 3-6 judgement;If similarity is bigger than g2, then it is assumed that
It is legal vehicle, is transferred to step 5;Wherein g1 could be arranged to 20% or other reasonable values, and its meaning is two vehicles of comparison
Image is that can confirm the situation of dissmilarity;And g2 is then to compare two car images for doubtful dissimilar situation, for example setting g2 is
50% or other reasonable values.
Condition 3-6, if u1>N or u2>N, then set up doubtful database D BW2 and in database D BW2 in output port server
In corresponding table information is set up by index of licence plate, and the number of times doubtful to the licence plate is marked, and is transferred to step 4;Other feelings
Condition is then transferred to step 5;Such as u1>N situation, then in database D BW2, set up following doubtful marking of cars table:【Car plate
D1, doubtful number of times v1】,【Car plate D2, doubtful number of times v2】,;Wherein, v1 and v2 are respectively used to mark the correspondence number-plate number D1 and D2
Doubtful number of times, be initially set to 0;It will first be retrieved subsequently under this square one and whether doubting for same car plate had in DBW2
Like information, if any, then doubtful counting how many times add up, until doubtful number of times is added to a threshold value, then by the car
The information of board is pushed to staff and carries out subsequent treatment;It should be noted that the car plate correspondence one each recorded is unique
Doubtful number of times mark, while in u1>N or u2>During n, by DWB2 tables to should the doubtful marking of cars table of car plate be synchronized to industry
It is engaged in platform, business platform often receives such synchronous meter and then plus 1 by the doubtful number of times of corresponding car plate, and by business platform
Judge to realize that being automatically pushed to staff carries out examination & verification processing when doubtful number of times exceedes threshold value.Threshold value is set to
3~20 or other reasonable values.
As shown in figure 4, the related procedure of business platform is as follows:
Step a:Business platform receive output port server upload warning data storehouse DBW1 in " doubtful to enter out conjunction table " and
Doubtful database D BW2, foundation includes the database D BW of corresponding doubtful marking of cars table information;
Step b:Judge whether there is corresponding car plate D1 in the DBW databases of business platform, if not provided, into step c;
Have as crossed, then the doubtful mark of the vehicle has been registered before showing, then into step d;
Step c:Newly-built car plate D1 for index doubtful information of vehicles table (D1, v), its doubtful number of times are set to 1;
Step d:Will the doubtful information of vehicles table of correspondence (D1, v) in car plate D1 doubtful number of times v add 1, and judge, if
Doubtful number of times exceedes the thresholding of setting, then is determined as fee evasion vehicle, is otherwise determined as legal vehicle.Or it is automatically pushed to work
Personnel carry out the doubtful situation processing of examination & verification, and according to circumstances can transfer specifying information from related charge station's server, such as enter out conjunction
The information such as table.Certainly, the car plate can also be (D2, v).
Step 4:Vehicle at call entry enters table information and shown to exit fee-collector or other related personnel, by
It makees further to make artificial judgement examination & verification at the scene;
Step 5:Terminate the process.
The invention provides a kind of system of highway fee evasion inspection, the method and approach of the technical scheme are implemented
A lot, described above is only the preferred embodiment of the present invention, it is noted that come for those skilled in the art
Say, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should be regarded as
Protection scope of the present invention.Each part being not known in the present embodiment can use prior art to be realized.